Welcome to Anbu Huang’s HomePage
About me:
I study diffusion/flow-matching models and multimodal foundation models, for which you can find more in my blog post.
On the Generative side: I study the “impossible triangle” of high fidelity, fast sampling, and strong controllability—designing training and inference methods (distillation, guidance, solver-aware sampling) that expand the Pareto frontier.
On the Multimodal side: I study to build native multimodal architectures that achieve a true unification of understanding and generation, enabling AI to perceive, reason, and create within a single, cohesive framework.
Contact Me: huanganbu@gmail.com
Previously: I focused on applied AI at Tencent, study recommendation systems, federated learning, and AI safety.
Selected Publications
From Trajectories to Operators — A Unified Flow Map Perspective on Generative Modeling
ICLR 2026 BlogPost Track.
Abstract. we reframe continuous-time generative modeling from integrating trajectories to learning two-time operators (flow maps). This operator view unifies diffusion, flow matching, and consistency model.
Navigating the Manifold — A Geometric Perspective on Diffusion-Based Inverse Problems
ICLR 2026 BlogPost Track.
Abstract. We show that a wide range of methods mostly instantiate two operator-splitting paradigms, i.e., posterior-guided sampling and clean-space local-MAP optimization.